HyperAI超神经

首页资讯论文教程数据集百科 SOTA LLM 模型天梯 GPU 天梯顶会

中文

HyperAI超神经

Semantic Segmentation On Nighttime Driving

评估指标

mIoU

评测结果

各个模型在此基准测试上的表现结果

模型名称	mIoU	Paper Title	Repository
DANNet (RefineNet)	42.36	DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation
Refign (DAFormer)	56.8	Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions
DANNet (DeepLab-v2)	44.98	DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation
TADP	60.8	Text-image Alignment for Diffusion-based Perception
CoDA	59.2	CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuning
CIConv	41.6	Zero-Shot Day-Night Domain Adaptation with a Physics Prior
DMAda	36.1	Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime	-
Refign (HRDA)	58.0	Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions
ERF-PSPNet	45.09	See Clearer at Night: Towards Robust Nighttime Semantic Segmentation through Day-Night Image Conversion	-
MGCDA	49.4	Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation
GCMA	45.6	Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation
DANNet (PSPNet)	47.70	DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation

0 of 12 row(s) selected.